A Collaborative Robot Cell for Random Bin-picking based on Deep Learning Policies and a Multi-gripper Switching Strategy

Albert Sonne Olesen; Benedek Benjamin Gergaly; Emil Albin Ryberg; Mads Riis Thomsen; Dimitrios Chrysostomou

doi:10.1016/j.promfg.2020.10.002

A Collaborative Robot Cell for Random Bin-picking based on Deep Learning Policies and a Multi-gripper Switching Strategy

Albert Sonne Olesen, Benedek Benjamin Gergaly, Emil Albin Ryberg, Mads Riis Thomsen, Dimitrios Chrysostomou^*

^*Corresponding author for this work

Research output: Contribution to journal › Conference article in Journal › Research › peer-review

12 Citations (Scopus)

101 Downloads (Pure)

Abstract

This paper presents the details of a collaborative robot cell assembled with off-the-shelf components designed for random bin-picking and robotic assembly applications. The proposed work investigates the benefits of combining an advanced RGB-D vision system and deep learning policies with a collaborative robot for the assembly of a mobile phone. An optimised version of YOLO is used to detect the arbitrarily placed components of the mobile phone on the working space. In order to overcome the challenges of grasping the various components of the mobile phone, a multi-gripper switching strategy is implemented using suction and multiple fingertips. Finally, the preliminary experiments performed with the proposed robot cell demonstrate that the increased learning capabilities of the robot achieve high performance in identifying the respective components of the mobile phone, grasping them accurately and performing the final assembly successfully.

Original language	English
Journal	Procedia Manufacturing
Volume	51
Pages (from-to)	3-10
Number of pages	8
ISSN	2351-9789
DOIs	https://doi.org/10.1016/j.promfg.2020.10.002
Publication status	Published - 19 Nov 2020
Event	30th International Conference on Flexible Automation and Intelligent Manufacturing - Athens, Greece Duration: 15 Jun 2021 → 18 Jun 2021 https://www.faimconference.org/

Conference

Conference	30th International Conference on Flexible Automation and Intelligent Manufacturing
Country/Territory	Greece
City	Athens
Period	15/06/2021 → 18/06/2021
Internet address	https://www.faimconference.org/

Bibliographical note

Publisher Copyright:
© 2020 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/) Peer-review under responsibility of the scientific committee of the FAIM 2021.

Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.

Keywords

random bin-picking
deep learning
Collaborative Robot
multi-gripper
industry 4.0

Access to Document

10.1016/j.promfg.2020.10.002Licence: CC BY-NC-ND 4.0

Open Access articleFinal published version, 1.32 MBLicence: CC BY-NC-ND 4.0

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{e26fd45ae3d94dce955a2fa4f4c230da,

title = "A Collaborative Robot Cell for Random Bin-picking based on Deep Learning Policies and a Multi-gripper Switching Strategy",

abstract = "This paper presents the details of a collaborative robot cell assembled with off-the-shelf components designed for random bin-picking and robotic assembly applications. The proposed work investigates the benefits of combining an advanced RGB-D vision system and deep learning policies with a collaborative robot for the assembly of a mobile phone. An optimised version of YOLO is used to detect the arbitrarily placed components of the mobile phone on the working space. In order to overcome the challenges of grasping the various components of the mobile phone, a multi-gripper switching strategy is implemented using suction and multiple fingertips. Finally, the preliminary experiments performed with the proposed robot cell demonstrate that the increased learning capabilities of the robot achieve high performance in identifying the respective components of the mobile phone, grasping them accurately and performing the final assembly successfully.",

keywords = "random bin-picking, deep learning, Collaborative Robot, multi-gripper, industry 4.0",

author = "Olesen, {Albert Sonne} and Gergaly, {Benedek Benjamin} and Ryberg, {Emil Albin} and Thomsen, {Mads Riis} and Dimitrios Chrysostomou",

note = "Publisher Copyright: {\textcopyright} 2020 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/) Peer-review under responsibility of the scientific committee of the FAIM 2021. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.; 30th International Conference on Flexible Automation and Intelligent Manufacturing, FAIM 2021 ; Conference date: 15-06-2021 Through 18-06-2021",

year = "2020",

month = nov,

day = "19",

doi = "10.1016/j.promfg.2020.10.002",

language = "English",

volume = "51",

pages = "3--10",

journal = "Procedia Manufacturing",

issn = "2351-9789",

publisher = "Elsevier",

url = "https://www.faimconference.org/",

}

TY - GEN

T1 - A Collaborative Robot Cell for Random Bin-picking based on Deep Learning Policies and a Multi-gripper Switching Strategy

AU - Olesen, Albert Sonne

AU - Gergaly, Benedek Benjamin

AU - Ryberg, Emil Albin

AU - Thomsen, Mads Riis

AU - Chrysostomou, Dimitrios

N1 - Publisher Copyright: © 2020 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/) Peer-review under responsibility of the scientific committee of the FAIM 2021. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.

PY - 2020/11/19

Y1 - 2020/11/19

N2 - This paper presents the details of a collaborative robot cell assembled with off-the-shelf components designed for random bin-picking and robotic assembly applications. The proposed work investigates the benefits of combining an advanced RGB-D vision system and deep learning policies with a collaborative robot for the assembly of a mobile phone. An optimised version of YOLO is used to detect the arbitrarily placed components of the mobile phone on the working space. In order to overcome the challenges of grasping the various components of the mobile phone, a multi-gripper switching strategy is implemented using suction and multiple fingertips. Finally, the preliminary experiments performed with the proposed robot cell demonstrate that the increased learning capabilities of the robot achieve high performance in identifying the respective components of the mobile phone, grasping them accurately and performing the final assembly successfully.

AB - This paper presents the details of a collaborative robot cell assembled with off-the-shelf components designed for random bin-picking and robotic assembly applications. The proposed work investigates the benefits of combining an advanced RGB-D vision system and deep learning policies with a collaborative robot for the assembly of a mobile phone. An optimised version of YOLO is used to detect the arbitrarily placed components of the mobile phone on the working space. In order to overcome the challenges of grasping the various components of the mobile phone, a multi-gripper switching strategy is implemented using suction and multiple fingertips. Finally, the preliminary experiments performed with the proposed robot cell demonstrate that the increased learning capabilities of the robot achieve high performance in identifying the respective components of the mobile phone, grasping them accurately and performing the final assembly successfully.

KW - random bin-picking

KW - deep learning

KW - Collaborative Robot

KW - multi-gripper

KW - industry 4.0

UR - https://www.sciencedirect.com/science/article/pii/S2351978920318576?via%3Dihub

UR - http://www.scopus.com/inward/record.url?scp=85099841105&partnerID=8YFLogxK

U2 - 10.1016/j.promfg.2020.10.002

DO - 10.1016/j.promfg.2020.10.002

M3 - Conference article in Journal

SN - 2351-9789

VL - 51

SP - 3

EP - 10

JO - Procedia Manufacturing

JF - Procedia Manufacturing

T2 - 30th International Conference on Flexible Automation and Intelligent Manufacturing

Y2 - 15 June 2021 through 18 June 2021

ER -

A Collaborative Robot Cell for Random Bin-picking based on Deep Learning Policies and a Multi-gripper Switching Strategy

Abstract

Conference

Bibliographical note

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

AI Cloud Service

Cite this

A Collaborative Robot Cell for Random Bin-picking based on Deep Learning Policies and a Multi-gripper Switching Strategy

Abstract

Conference

Bibliographical note

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Equipment

AI Cloud Service

Cite this